An image change detection algorithm based on Markov random field models

IEEE Transactions on Geoscience and Remote Sensing - Tập 40 Số 8 - Trang 1815-1823 - 2002
T. Kasetkasem1, P.K. Varshney1
1Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA

Tóm tắt

This paper addresses the problem of image change detection (ICD) based on Markov random field (MRF) models. MRF has long been recognized as an accurate model to describe a variety of image characteristics. Here, we use the MRF to model both noiseless images obtained from the actual scene and change images (CIs), the sites of which indicate changes between a pair of observed images. The optimum ICD algorithm under the maximum a posteriori (MAP) criterion is developed under this model. Examples are presented for illustration and performance evaluation.

Từ khóa

#Detection algorithms #Markov random fields #Pixel #Character recognition #Image recognition #Image texture analysis #Layout #Computational Intelligence Society #Change detection algorithms

Tài liệu tham khảo

wiemker, 1997, an iterative spectral-spatial bayesian labeling approach for unsupervised robust change detection on remotely sensed multispectral imagery, Proc CAIP, 263 10.1109/18.481788 10.1007/978-1-4612-1904-0 van trees, 1968, Detection Estimation and Modulation Theory Part 1 10.1109/36.843012 10.1109/83.753737 10.1109/34.31443 10.1109/36.718860 kasetkasem, 0, Image analysis methods based on Markov random field models usgs, 1995, Discussion of satellite image products Part 1 introduction color images 10.1109/36.239913 lunetta, 1999, Remote Sensing Change Detection bremaud, 1999, Markov Chains Gibbs Field Monte Carlo Simulation and Queues, 10.1007/978-1-4757-3124-8 10.1007/978-3-642-97522-6 begas, 1986, on the statistical analysis of dirty pictures, J R Stat Soc, b 48, 259 10.1109/TPAMI.1984.4767596 10.1007/978-3-662-03978-6 10.1080/01431168908903939 10.1109/36.843009